Skills
skills/sieteunoseis/cisco-perfmon/cisco-perfmon-cli/Gen Agent Trust Hub

cisco-perfmon-cli

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes the cisco-perfmon CLI tool to retrieve performance statistics from Cisco CUCM clusters.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by ingesting data from remote Cisco CUCM PerfMon APIs. Ingestion points: Performance data is retrieved via cisco-perfmon collect, list-objects, and watch commands. Boundary markers: No delimiters or instructions to ignore embedded content are present in the command outputs. Capability inventory: The agent can execute cisco-perfmon commands and manage session handles. Sanitization: No evidence of sanitization or validation for retrieved counter data is provided in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 09:49 PM